WizardCoder 34B surpasses GPT4 on HumanEval(twitter.com)1 points·by bytefactory·vor 3 Jahren·1 commentstwitter.comWizardCoder 34B surpasses GPT4 on HumanEvalhttps://twitter.com/WizardLM_AI/status/16953968812188593741 commentsPost comment[–]bytefactory·vor 3 JahrenreplyWizardLM claims to have beaten GPT4 on HumanEval with 73.2% @ Pass1 to GPT4s 67% (in the original GPT4 report).Big, if true. Their own testing puts present GPT4 at 82%, but 73.2% still seems very competitive.
Big, if true. Their own testing puts present GPT4 at 82%, but 73.2% still seems very competitive.